INDEX

Explanations

instances of the word "original" and its variations within the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 الحره

-0.51

Liefs

-0.48

RefNanny

-0.47

 TextAppearance

-0.46

Groetjes

-0.45

 spons

-0.45

ervlak

-0.43

ActionListener

-0.43

 Rook

-0.43

 boom

-0.43

POSITIVE LOGITS

Original

0.77

 Original

0.73

original

0.66

old

0.63

 ORIGINAL

0.59

ORIGINAL

0.58

EndInit

0.57

########.

0.54

 differentiation

0.54

ViewImports

0.52

Activations Density 0.333%

instances of the word "original" and its variations within the text

No Comments

No Known Activations